Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add seldonframe/reelier --skill reelier-replaygit clone --depth 1 https://github.com/seldonframe/reelierWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/seldonframe/reelier/reelier-replay)<a href="https://agentmods.dev/skills/seldonframe/reelier/reelier-replay"><img src="https://agentmods.dev/badge/skills/seldonframe/reelier/reelier-replay/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/seldonframe/reelier/reelier-replay"><img src="https://agentmods.dev/badge/skills/seldonframe/reelier/reelier-replay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.01367 |
| Opus 5 | $0.00037 | $0.00683 |
| Sonnet 5 | $0.00015 | $0.00273 |
| Haiku 4.5 | $0.00007 | $0.00137 |
Grade A, and why
reelier-replay scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reelier — record once, replay forever
Reelier turns a deterministic sequence of tool calls into a SKILL.md file
that replays for free (zero LLM calls) instead of being re-reasoned from
scratch every time. This skill teaches you when to reach for it.
written against reelier 0.32.x. reelier --help on the installed CLI is
always authoritative.
How to run Reelier — in this order
- If the
reelier_*MCP tools are connected, use them. Structured results, no shell. - Otherwise run the CLI:
npx -y reelier <command>. Nothing needs to be installed first. - If neither is available — no shell access and no MCP tools — say plainly which is missing and stop. Never describe a step as done when it did not run.
The tool name is not the command name. Two of them differ, and guessing
gets you a usage error — there is no reelier replay subcommand:
| MCP tool | CLI command |
|---|---|
reelier_scan |
npx -y reelier scan |
reelier_from_session |
npx -y reelier from-session |
reelier_replay |
npx -y reelier run |
reelier_push |
npx -y reelier push |
reelier_diff |
npx -y reelier diff |
Optional, and worth offering once: adding reelier serve to the user's own
project MCP config makes path 1 available and is faster than npx on every
call.
{ "mcpServers": { "reelier": { "command": "npx", "args": ["-y", "reelier", "serve"] } } }
The honesty boundary — read this first
Reelier can only replay deterministic tool calls: its own HTTP
builtins (http.get/http.post) and MCP server tool calls
(mcp__<server>__<tool>). It cannot replay:
- File edits (
Edit,Write,NotebookEdit) - Shell commands (
Bash) - Reads/searches (
Read,Grep,Glob) - Subagent dispatch (
Task) - Anything non-deterministic (web search results that vary, LLM-generated content, timestamps that aren't parameterized)
Never tell a user "I'll replay this session for you" about a coding
session. A session that was mostly edits and greps has nothing
replayable in it, and reelier_scan/reelier_from_session will say so
honestly (an empty result, not an error) — that's expected, not a bug.
Only offer to freeze a task when it was actually a sequence of API/MCP
calls: pulling data from a CRM, hitting a deploy-status endpoint, walking
a ticketing system, querying a database via its MCP server, and similar.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 116 lines · 75 tokens per session scan A 8ac5829cd6ad
reelier-replay is a skill published in the GitHub repository seldonframe/reelier (3 stars, last pushed 17d ago), licensed MIT. It adds 75 tokens to every session and 1,367 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
robin
Use whenever an agent creates, updates, reviews, or completes a GitHub pull request. Detect whether Robin is installed in the repository; when it is, automatically drive the PR through a bounded review, verified-fix, reply, thread-resolution, re-review, authorized-merge, and cleanup loop without requiring the user to…
shell-scripting
Use this skill when writing bash or zsh scripts, parsing arguments, handling errors, or automating CLI workflows. Triggers on bash scripting, shell scripts, argument parsing, process substitution, here documents, signal trapping, exit codes, and any task requiring portable shell script development.
ai-unity-asset-pipeline
Build, install, run, and verify a reusable image-to-game-ready-3D pipeline for Unity with controlled ImageGen references, approved AI mesh providers, Blender MCP/CLI, modular era catalogs, Blender retopology/LOD/pivot processing, and Unity import/render proof. Use for 2D-to-3D assets, vehicles, aircraft, ships…
memory-lint
Deterministic integrity check for the agent-memory layer. Use after a memory review, before committing memory/ changes, or in CI to catch decay miscounts — facts archived while still referenced, an id in both continuity and the archive, tier or supersession drift — and leaked secrets or PII (credentials, tokens…
second-opinion
Generate a fresh-context review snapshot of the current task for a clean-memory AI reviewer (any vendor or a clean session). Use at a milestone that looks complete, or when blocked, uncertain, or facing a risky change, to get an independent second opinion before proceeding; shows a security advisory before exporting…
apply-critique
Apply a fresh-context reviewer's critique to the current work through a bounded, validated, human-gated loop. Use after a second-opinion review returns a critique — parse it, plan a few scoped fixes, run the build/tests and memory-lint, then summarize what was applied versus rejected and why.